1
0
Fork 0

Improve a bit the support for ppt files

This commit is contained in:
jvoisin 2019-10-17 23:02:17 +02:00
parent a389cc760a
commit 655c19d17d
1 changed files with 10 additions and 9 deletions

View File

@ -77,25 +77,26 @@ class MSOfficeParser(ZipParser):
self.files_to_keep = set(map(re.compile, { # type: ignore self.files_to_keep = set(map(re.compile, { # type: ignore
r'^\[Content_Types\]\.xml$', r'^\[Content_Types\]\.xml$',
r'^_rels/\.rels$', r'^_rels/\.rels$',
r'^word/_rels/document\.xml\.rels$', r'^(?:word|ppt)/_rels/document\.xml\.rels$',
r'^word/_rels/footer[0-9]*\.xml\.rels$', r'^(?:word|ppt)/_rels/footer[0-9]*\.xml\.rels$',
r'^word/_rels/header[0-9]*\.xml\.rels$', r'^(?:word|ppt)/_rels/header[0-9]*\.xml\.rels$',
r'^ppt/slideLayouts/_rels/slideLayout[0-9]+\.xml\.rels$',
# https://msdn.microsoft.com/en-us/library/dd908153(v=office.12).aspx # https://msdn.microsoft.com/en-us/library/dd908153(v=office.12).aspx
r'^word/stylesWithEffects\.xml$', r'^(?:word|ppt)/stylesWithEffects\.xml$',
})) }))
self.files_to_omit = set(map(re.compile, { # type: ignore self.files_to_omit = set(map(re.compile, { # type: ignore
r'^customXml/', r'^customXml/',
r'webSettings\.xml$', r'webSettings\.xml$',
r'^docProps/custom\.xml$', r'^docProps/custom\.xml$',
r'^word/printerSettings/', r'^(?:word|ppt)/printerSettings/',
r'^word/theme', r'^(?:word|ppt)/theme',
r'^word/people\.xml$', r'^(?:word|ppt)/people\.xml$',
r'^word/numbering\.xml$', r'^(?:word|ppt)/numbering\.xml$',
# we have an allowlist in self.files_to_keep, # we have an allowlist in self.files_to_keep,
# so we can trash everything else # so we can trash everything else
r'^word/_rels/', r'^(?:word|ppt)/_rels/',
})) }))
if self.__fill_files_to_keep_via_content_types() is False: if self.__fill_files_to_keep_via_content_types() is False: